Internal response disclosure via nested sitemap fetch
Published Aug 20, 2026 · Updated Aug 20, 2026
Server-side request forgery in LangChain Community 0.4.2 and earlier allows attackers to read internal HTTP responses via crafted sitemaps. In SitemapLoader.parse_sitemap, the same-domain check runs on url loc entries, but nested sitemap loc values are passed directly to scrape_all(), which reaches aiohttp GET with no domain or private-address validation. Exposure requires an application to ingest attacker-influenced sitemap content; when that workflow is reachable, returned Documents can disclose fetched intranet or cloud-metadata content.
Summary
What happened
Server-side request forgery in LangChain Community 0.4.2 and earlier allows attackers to read internal HTTP responses via crafted sitemaps. In SitemapLoader.parse_sitemap, the same-domain check runs on url loc entries, but nested sitemap loc values are passed directly to scrape_all(), which reaches aiohttp GET with no domain or private-address validation. Exposure requires an application to ingest attacker-influenced sitemap content; when that workflow is reachable, returned Documents can disclose fetched intranet or cloud-metadata content.
The record
- CVE
- CVE-2026-72848
- Published
- Aug 20, 2026
- Updated
- Aug 20, 2026
- Vendor
- LangChain
- Product
- LangChain Community
- Classifications
- CWE-918, T1190
- Attack vector
- network
- Privileges
- Unavailable
Timeline
How it unfolded
- Aug 20, 2026CVE publishedPublication date reported by the CVE source.
- Aug 20, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=0 <=0.4.2
What conditions does exploitation require?
What is affected?
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
- Issue 38814 proof of concept for recursive sitemap SSRFproof of concept · demonstrated
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo